AI 中文总结
针对现有多智能体系统演化方法的权衡问题，提出基于ReAct的OptiMAS优化器，通过双轨记忆机制在四类基准上优于或媲美手工系统与现有演化方法，为自动化MAS演化奠定里程碑。
AI 中文摘要
多智能体系统（MAS）的自动化演化在减少设计和优化基于大语言模型（LLM）的智能体架构所需的人工工作量方面具有巨大潜力。然而，现有的基于搜索的范式面临着一个根本权衡：扩大优化范围会加剧演化不稳定性，而离散的分支-丢弃搜索则会隔离不同谱系间的见解。为解决这些局限，我们提出了一种基于统一ReAct基础设施的连续、数据驱动的优化范式，该范式可协调广泛的优化范围与操作稳定性。在该范式下，我们提出了OptiMAS，这是一种与任务无关的智能体优化器，它利用文本交互轨迹和任务反馈作为端到端MAS演化的损失信号。配备新颖的双轨记忆机制后，OptiMAS可在 extended optimization horizons 期间维持性能提升。在四个异构智能体基准上，使用三种不同规模和可访问性的LLM骨干进行评估，结果表明，OptiMAS与领域专用的手工设计系统及现有演化方法相比，始终能达到有竞争力或更优的准确率。我们的工作为实现稳健、自动化的MAS演化奠定了实用里程碑。
英文摘要
Automated evolution of Multi-Agent Systems (MAS) holds significant potential for reducing the manual effort required to design and optimize LLM-based agent architectures. However, extant search-based paradigms face a fundamental trade-off, where an expanded optimization scope exacerbates evolutionary instability, while discrete branch-and-discard search isolates insights across lineages. To address these limitations, we propose a continuous, data-driven optimization paradigm built upon a unified ReAct-based infrastructure that reconciles a broad optimization scope with operational stability. Under this paradigm, we present OptiMAS, a task-agnostic agentic optimizer that leverages textual interaction trajectories and task feedback as loss signals for end-to-end MAS evolution. Equipped with a novel dual-track memory mechanism, OptiMAS sustains performance improvement over extended optimization horizons. Evaluation on four heterogeneous agentic benchmarks with three varying scale and accessibility LLM backbones, demonstrates that OptiMAS consistently achieves competitive or superior accuracy relative to both domain-specialized hand-crafted systems and existing evolutionary methods. Our work establishes a practical milestone toward robust, automated MAS evolution.
CommentsEMNLP 2026
